HMM-based European Portuguese TTS system. Barros, M. J.; Maia, R.; Tokuda, K.; Resende Jr., F. G. V; and Freitas, D. R. d. S. In Eurospeech 2005 - Interspeech 2005. Proceedings of the 9th European Conference on Speech Communication and Technology, pages 2581-2584, Lisbon, Portugal. September 4-8, 2005.
HMM-based European Portuguese TTS system [link]Paper  abstract   bibtex   
The main purpose of the work here presented consists in applying a speech synthesis technique based on Hidden Markov Models (HMMs) to European Portuguese (EP), in order to build an HMMbased EP Text-to-Speech (TTS) System. The HMM-based speech synthesis technique (HSS) was originally tested for Japanese, but it has already been tested for other languages, such as English and Brazilian Portuguese. In fact, HSS comprises a compact module, being able to be applied to different languages. In the implemented TTS system, the speech waveform is generated by means of HMMs trained for an EP database, that are selected according to a set of automatically generated binary decision trees.
@inproceedings{barros_hmm-based_2005,
	Address = {Lisbon, Portugal. September 4-8, 2005},
	Author = {Barros, Maria João and Maia, Ranniery and Tokuda, Keiichi and Resende Jr., Fernando Gil V and Freitas, Diamantino Rui da Silva},
	Booktitle = {Eurospeech 2005 - Interspeech 2005. Proceedings of the 9th European Conference on Speech Communication and Technology},
	Date = {2005},
	Date-Modified = {2016-09-24 18:55:58 +0000},
	File = {Attachment:files/882/Barros et al. - 2005 - HMM-based European Portuguese TTS system.pdf:application/pdf},
	Keywords = {HMM, Portuguese, speech synthesis, speech technology, text-to-speech, text-to-speech system},
	Pages = {2581-2584},
	Title = {HMM-based European Portuguese TTS system},
	Url = {http://www.isca-speech.org/archive/interspeech_2005/i05_2581.html},
	Abstract = {The main purpose of the work here presented consists in applying a speech synthesis technique based on Hidden Markov Models (HMMs) to European Portuguese (EP), in order to build an HMMbased EP Text-to-Speech (TTS) System. The HMM-based speech synthesis technique (HSS) was originally tested for Japanese, but it has already been tested for other languages, such as English and Brazilian Portuguese. In fact, HSS comprises a compact module, being able to be applied to different languages. In the implemented TTS system, the speech waveform is generated by means of HMMs trained for an EP database, that are selected according to a set of automatically generated binary decision trees.},
	Bdsk-File-1 = {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},
	Bdsk-Url-1 = {http://www.isca-speech.org/archive/interspeech_2005/i05_2581.html}}
Downloads: 0